Carleton University
Automatic Cephalometric Landmark Detection on 2D X-Ray Images Using a Deep Learning Model and Rule-Based Knowledge
Abstract
dc:description.abstractObjectives: Cephalometric analysis is commonly employed in orthodontic diagnosis. Identification of anatomical landmarks on Cephalograms is the essential part of this analy- sis. Traditionally, clinicians have manually identified landmarks, but it is time-consuming and prone to errors. The purpose of this study is to automate the landmarks localization. Methods: 300 digital Cephalograms were randomly selected from the archive of a private orthodontic clinic. 19 important landmarks which are commonly used in most Cephalo- metric analyses, were chosen. An expert orthodontist manually annotated these landmarks. A hybrid approach was implemented for landmark localization. First, a neural network model was used to provide an initial prediction of each landmark’s location. Then for certain key landmarks, their locations were refined using image processing techniques guided by domain knowledge. Results: The total mean error was achieved at 1.57 in mm. These findings indicate that our method has strong accuracy, even for complex anatomical structures.
Degree
thesis:*- Name thesis:degree_name
- Master of Computer Science (M.C.S.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Data Science, Analytics, and Artificial Intelligence
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Hekmatnia, Elham
Subjects
dc:subject × 2Rights
dc:rights- Statement dc:rights
-
- Copyright © 2025 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en